lucataco/flux-dev-multi-lora 🔢🖼️📝❓✓ → 🖼️

▶️ 1.8M runs 📅 Aug 2024 ⚙️ Cog 0.14.10 🔗 GitHub ⚖️ License
image-to-image lora text-to-image

About

FLUX.1-Dev Multi LoRA Explorer

Example Output

Prompt:

"pnt style Illustration of TOK with purple hair"

Output

Example output

Performance Metrics

11.59s Prediction Time
11.60s Total Time
All Input Parameters 
{
  "prompt": "pnt style Illustration of TOK with purple hair",
  "hf_loras": [
    "https://replicate.delivery/yhqm/9vSmRCa8Vv7bFtKfCfXTRzTq4X71tZW0LtLCb1l49bTSo8TTA/trained_model.tar",
    "https://civitai.com/api/download/models/735262?type=Model&format=SafeTensor"
  ],
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "num_inference_steps": 28
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image mode. The aspect ratio of your output will match this image
prompt (required) Type: string
Prompt for generated image
hf_loras Type: array
Huggingface path, or URL to the LoRA weights. Ex: alvdansen/frosting_lane_flux
lora_scales Type: array
Scale for the LoRA weights. Default value is 0.8
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
aspect_ratio Default: 1:1
Aspect ratio for the generated image
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3.5Range: 0 - 10
Guidance scale for the diffusion process
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of inference steps
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
Using seed: 10430
Prompt: pnt style Illustration of TOK with purple hair
txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:10,  2.48it/s]
  7%|▋         | 2/28 [00:00<00:09,  2.69it/s]
 11%|█         | 3/28 [00:01<00:09,  2.59it/s]
 14%|█▍        | 4/28 [00:01<00:09,  2.55it/s]
 18%|█▊        | 5/28 [00:01<00:09,  2.53it/s]
 21%|██▏       | 6/28 [00:02<00:08,  2.51it/s]
 25%|██▌       | 7/28 [00:02<00:08,  2.50it/s]
 29%|██▊       | 8/28 [00:03<00:08,  2.50it/s]
 32%|███▏      | 9/28 [00:03<00:07,  2.50it/s]
 36%|███▌      | 10/28 [00:03<00:07,  2.49it/s]
 39%|███▉      | 11/28 [00:04<00:06,  2.49it/s]
 43%|████▎     | 12/28 [00:04<00:06,  2.49it/s]
 46%|████▋     | 13/28 [00:05<00:06,  2.49it/s]
 50%|█████     | 14/28 [00:05<00:05,  2.49it/s]
 54%|█████▎    | 15/28 [00:05<00:05,  2.49it/s]
 57%|█████▋    | 16/28 [00:06<00:04,  2.49it/s]
 61%|██████    | 17/28 [00:06<00:04,  2.49it/s]
 64%|██████▍   | 18/28 [00:07<00:04,  2.49it/s]
 68%|██████▊   | 19/28 [00:07<00:03,  2.49it/s]
 71%|███████▏  | 20/28 [00:07<00:03,  2.49it/s]
 75%|███████▌  | 21/28 [00:08<00:02,  2.49it/s]
 79%|███████▊  | 22/28 [00:08<00:02,  2.49it/s]
 82%|████████▏ | 23/28 [00:09<00:02,  2.49it/s]
 86%|████████▌ | 24/28 [00:09<00:01,  2.49it/s]
 89%|████████▉ | 25/28 [00:09<00:01,  2.49it/s]
 93%|█████████▎| 26/28 [00:10<00:00,  2.49it/s]
 96%|█████████▋| 27/28 [00:10<00:00,  2.49it/s]
100%|██████████| 28/28 [00:11<00:00,  2.49it/s]
100%|██████████| 28/28 [00:11<00:00,  2.50it/s]
Version Details
Version ID
ad0314563856e714367fdc7244b19b160d25926d305fec270c9e00f64665d352
Version Created
June 11, 2025
Run on Replicate →